This work aims to recognize signs which have both manual and nonmanual components by providing a sequential belief-based fusion mechanism. We propose a methodology based on belief functions for fusing extracted manual and non-manual features in a sequential two-step approach. The belief functions based on the likelihoods of the hidden Markov models are used to decide whether there is an uncerta...

We present a new approach to the amenability of groupoids (both in the measure theoretical and the topological setups) based on using Markov operators. We introduce the notion of an invariant Markov operator on a groupoid and show that the Liouville property (absence of non-trivial bounded harmonic functions) for such an operator implies amenability of the groupoid. Moreover, the groupoid actio...

Algebraic Geometry of Hidden Markov and Related Models

The problem of acquiring multiple tasks from demonstration is typically divided in two sequential processes: (1) the segmentation or identification of different subgoals/subtasks and (2) a separate learning process that parameterizes a control policy for each subtask. As a result, segmentation criteria typically neglect the characteristics of control policies and rely instead on simplified mode...

this paper presents a discrete-time single-server finite buffer n threshold policy queue with renewal input and discretemarkovian service process. the server terminates service whenever the system becomes empty, and recommencesservice as soon as the number of waiting customers in the queue is n. we obtain the system-length distributionsat pre-arrival and arbitrary epochs using the supplementary...

This paper, presents ongoing work that extends MetaProbLog with Most Probable Explanation (MPE) inference method. The MPE inference method is widely used in Hidden Markov Models in order to derive the most likely states of a model. Recently, we started developing an application that uses MetaProbLog to models phonocardiograms. We target to use this application in order to diagnose heart disease...

Article history: Received 15 September 2008 Received in revised form 10 March 2009 Accepted 18 March 2009

We consider a threshold type control mechanism for dynamic setup/release of λ-channels in optical networks. There are two types of costs for the control mechanism: the setup/release cost and the operation cost. For such a control mechanism, there is a corresponding Markov model with high complexity. By state aggregation, we are able to identify a semi-Markov process that is simpler to analyze. ...